4-bit Open on Hugging Face
Parameters
7.5B
Weights (est.)
≈ 4.2 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/Hunyuan-7B-Instruct-2508-4bit --prompt "Hello"
Details
- Base model
- tencent/Hunyuan-7B-Instruct (quantized)
- Vendor
- tencent
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 45 in the last 30 days · 415 all time · 0 likes
- Published
- 2025-08-04 · updated 2025-08-04 (1y ago)
- Tags
- hunyuan_v1_dense
Other MLX builds of tencent/Hunyuan-7B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hunyuan-7B-Instruct-3bit | 3-bit | ≈ 3.3 GB | 8 GB+ | 18 |
| Hunyuan-7B-Instruct-2508-4bit (this one) | 4-bit | ≈ 4.2 GB | 8 GB+ | 45 |
| Hunyuan-7B-Instruct-4bit | 4-bit | ≈ 4.2 GB | 8 GB+ | 41 |
| Hunyuan-7B-Instruct-6bit | 6-bit | ≈ 6.1 GB | 16 GB+ | 20 |
| Hunyuan-7B-Instruct-2508-8bit | 8-bit | ≈ 8.0 GB | 16 GB+ | 33 |
| Hunyuan-7B-Instruct-8bit | 8-bit | ≈ 8.0 GB | 16 GB+ | 24 |
| Hunyuan-7B-Instruct-fp16 | fp16 | ≈ 15.0 GB | 24 GB+ | 24 |